COORDINATION OF MULTIPLE INTELLIGENT SOFTWARE AGENTS

TLDR

The task for which information is requested is explicitly represented and supported through agent collaboration. The paper investigates techniques for developing distributed, adaptive information agent collections that coordinate to retrieve, filter, fuse information and anticipate user needs, and presents a reusable system architecture and component set for structuring such agents. The system comprises interface agents that receive user specifications and deliver results, task agents that formulate problem‑solving plans and execute them via inter‑agent queries, and information agents that provide intelligent access to heterogeneous sources, with information gathering integrated into decision support and user preferences guiding coordination. We have implemented this system framework and are developing collaborating agents in diverse complex real‑world tasks such as organizational decision making, investment counseling, health care and electronic commerce.

Abstract

We are investigating techniques for developing distributed and adaptive collections of information agents that coordinate to retrieve, filter and fuse information relevant to the user, task and situation, as well as anticipate user's information needs. In our system of agents, information gathering is seamlessly integrated with decision support. The task for which particular information is requested of the agents does not remain in the user's head but it is explicitly represented and supported through agent collaboration. In this paper we present the distributed system architecture, agent collaboration interactions, and a reusable set of software components for structuring agents. The system architecture has three types of agents: Interface agents interact with the user receiving user specifications and delivering results. They acquire, model, and utilize user preferences to guide system coordination in support of the user's tasks. Task agents help users perform tasks by formulating problem solving plans and carrying out these plans through querying and exchanging information with other software agents. Information agents provide intelligent access to a heterogeneous collection of information sources. We have implemented this system framework and are developing collaborating agents in diverse complex real world tasks, such as organizational decision making, investment counseling, health care and electronic commerce.